© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 16315
    Prev
    Next
    INDEX
    Explanations

    legal agreements and binding language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.64
    تقاوى
    -0.64
    évaluateur
    -0.62
    featureID
    -0.54
    ChildScrollView
    -0.54
     gynhyrchwyd
    -0.53
     ComVisible
    -0.51
    MessageOf
    -0.51
    IsContent
    -0.48
    windowFixed
    -0.48
    POSITIVE LOGITS
     binding
    2.56
     bound
    2.53
     bind
    2.52
     Binding
    2.27
     bond
    2.27
     binds
    2.25
     Bind
    2.20
    bind
    2.14
     Bound
    2.11
     bindings
    2.11
    Activations Density 1.258%

    No Known Activations